Assessing naming errors using an automated machine learning approach.

OBJECTIVE: After left hemisphere stroke, 20%-50% of people experience language deficits, including difficulties in naming. Naming errors that are semantically related to the intended target (e.g., producing "violin" for picture HARP) indicate a potential impairment in accessing knowledge of word forms and their meanings. Understanding the cause of naming impairments is crucial to better modeling of language production as well as for tailoring individualized rehabilitation. However, evaluation of naming errors is typically by subjective and laborious dichotomous classification. As a result, these evaluations do not capture the degree of semantic similarity and are susceptible to lower interrater reliability because of subjectivity. METHOD: We investigated whether a computational linguistic measure using word2vec (Mikolov, Chen, et al., 2013) addressed these limitations by evaluating errors during object naming in a group of patients during the acute stage of a left-hemisphere stroke (N = 105). RESULTS: Pearson correlations demonstrated excellent convergent validity of word2vec's semantically related estimates of naming errors and independent tests of access to lexical-semantic knowledge (p < .0001). Further, multiple regression analysis showed word2vec's semantically related estimates were significantly better than human error classification at predicting performance on tests of lexical-semantic knowledge. CONCLUSIONS: Useful to both theorists and clinicians, our word2vec-based method provides an automated, continuous, and objective psychometric measure of access to lexical-semantic knowledge during naming. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Enhancing the Efficiency of Confrontation Naming Assessment for Aphasia Using Computer Adaptive Testing.

Purpose In this study, we investigated the agreement between the 175-item Philadelphia Naming Test (PNT; Roach, Schwartz, Martin, Grewal, & Brecher, 1996 ) and a 30-item computer adaptive PNT (PNT-CAT; Fergadiotis, Kellough, & Hula, 2015 ; Hula, Kellough, & Fergadiotis, 2015 ) created using item response theory (IRT) methods. Method The full PNT and the PNT-CAT were administered to 47 participants with aphasia in counterbalanced order. Latent trait-naming ability estimates for the 2 PNT versions were analyzed in a Bayesian framework, and the agreement between them was evaluated using correlation and measures of constant, variable, and total error. We also evaluated the extent to which individual pairwise differences were credibly greater than 0 and whether the IRT measurement model provided an adequate indication of the precision of individual score estimates. Results The agreement between the PNT and the PNT-CAT was strong, as indicated by high correlation ( r = .95, 95% CI [.92, .97]), negligible bias, and low variable and total error. The number of statistically robust pairwise score differences did not credibly exceed the Type I error rate, and the precision of individual score estimates was reasonably well predicted by the IRT model. Discussion The strong agreement between the full PNT and the PNT-CAT suggests that the latter is a suitable measurement of anomia in group studies. The relatively robust estimates of score precision also suggest that the PNT-CAT can be useful for the clinical assessment of anomia in individual cases. Finally, the IRT methods used to construct the PNT-CAT provide a framework for additional development to further reduce measurement error. Supplemental Material https://doi.org/10.23641/asha.8202176.

Structural Prediction in Aphasia: Evidence from either.

Young neurotypical adults engage in prediction during language comprehension (e.g., Altmann & Kamide, 1999; Staub & Clifton, 2006; Yoshida, Dickey & Sturt, 2013). The role of prediction in aphasic comprehension is less clear. Some evidence suggests that lexical prediction may be spared in aphasia (Dickey et al., 2014; Love & Webb, 1977; cf. Mack et al, 2013), and there is even indication that structural prediction may be spared in some people with aphasia (PWA; e.g. Hanne, Burchert, De Bleser, & Vashishth, 2015). The current self-paced reading experiment manipulated the presence of either to examine structural prediction among PWA and a set of similar-aged neurotypical control participants. Consistent with intact structural prediction for both groups of participants, when either preceded a disjunction, reading times were faster on the or and second disjunct (cf. Staub & Clifton, 2006). For neurotypical controls, this effect of the presence vs. absence of either shrank reliably as more experimental items were encountered, whereas for PWA there was a non-significant trend for it to grow as more experimental items were encountered. These findings indicate that PWA and older neurotypical individuals can use a lexical cue to predict the structural form of upcoming material during comprehension, but that on-line adaptation to patterns in the local context may be different for the two groups.